Vision Transformer for COVID-19 CXR Diagnosis using Chest X-ray Feature Corpus
arXiv:2103.07055
Abstract
Under the global COVID-19 crisis, developing robust diagnosis algorithm for COVID-19 using CXR is hampered by the lack of the well-curated COVID-19 data set, although CXR data with other disease are abundant. This situation is suitable for vision transformer architecture that can exploit the abundant unlabeled data using pre-training. However, the direct use of existing vision transformer that uses the corpus generated by the ResNet is not optimal for correct feature embedding. To mitigate this problem, we propose a novel vision Transformer by using the low-level CXR feature corpus that are obtained to extract the abnormal CXR features. Specifically, the backbone network is trained using large public datasets to obtain the abnormal features in routine diagnosis such as consolidation, glass-grass opacity (GGO), etc. Then, the embedded features from the backbone network are used as corpus for vision transformer training. We examine our model on various external test datasets acquired from totally different institutions to assess the generalization ability. Our experiments demonstrate that our method achieved the state-of-art performance and has better generalization capability, which are crucial for a widespread deployment.
arXiv comment10 pages
References in corpus (7)
- An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
- Covid-19: Automatic detection from X-Ray images utilizing Transfer Learning with Convolutional Neural Networks
- Confounding variables can degrade generalization performance of radiological deep learning models
- COVIDX-Net: A Framework of Deep Learning Classifiers to Diagnose COVID-19 in X-Ray Images
- Viral Pneumonia Screening on Chest X-ray Images Using Confidence-Aware Anomaly Detection
- The challenges of deploying artificial intelligence models in a rapidly evolving pandemic
- Weakly Supervised Lesion Localization With Probabilistic-CAM Pooling